{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:24CFZMU4QQSDJDWSCYFRJBA2SF","short_pith_number":"pith:24CFZMU4","schema_version":"1.0","canonical_sha256":"d7045cb29c8424348ed2160b14841a9178d8a20468d685b31da24b1132370d1f","source":{"kind":"arxiv","id":"1812.04352","version":3},"attestation_state":"computed","paper":{"title":"Layer-Parallel Training of Deep Residual Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"E.C. Cyr, J.B. Schroder, L. Ruthotto, N.R. Gauger, S. G\\\"unther","submitted_at":"2018-12-11T12:26:48Z","abstract_excerpt":"Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, par"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.04352","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-12-11T12:26:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb1bd211e049fc5552314f121493b6afb65cf9aff3a06ee35f34b7052ce1d78d","abstract_canon_sha256":"d2ba0fa0c3fa9c0abdaeabfa63bae478145c108cad7c129a41b807ca44c1e0b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:36.985754Z","signature_b64":"2ficUcnMPwsTNC+EfAVh4iy78QHSfDegJjvMKl7/2dxzgdpQjKJ58LlI9qsUfLscixDCxPgzVHDei6AsS0B7Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7045cb29c8424348ed2160b14841a9178d8a20468d685b31da24b1132370d1f","last_reissued_at":"2026-05-17T23:39:36.984958Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:36.984958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Layer-Parallel Training of Deep Residual Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"E.C. Cyr, J.B. Schroder, L. Ruthotto, N.R. Gauger, S. G\\\"unther","submitted_at":"2018-12-11T12:26:48Z","abstract_excerpt":"Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04352","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.04352","created_at":"2026-05-17T23:39:36.985057+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04352v3","created_at":"2026-05-17T23:39:36.985057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04352","created_at":"2026-05-17T23:39:36.985057+00:00"},{"alias_kind":"pith_short_12","alias_value":"24CFZMU4QQSD","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_16","alias_value":"24CFZMU4QQSDJDWS","created_at":"2026-05-18T12:31:59.375834+00:00"},{"alias_kind":"pith_short_8","alias_value":"24CFZMU4","created_at":"2026-05-18T12:31:59.375834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF","json":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF.json","graph_json":"https://pith.science/api/pith-number/24CFZMU4QQSDJDWSCYFRJBA2SF/graph.json","events_json":"https://pith.science/api/pith-number/24CFZMU4QQSDJDWSCYFRJBA2SF/events.json","paper":"https://pith.science/paper/24CFZMU4"},"agent_actions":{"view_html":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF","download_json":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF.json","view_paper":"https://pith.science/paper/24CFZMU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04352&json=true","fetch_graph":"https://pith.science/api/pith-number/24CFZMU4QQSDJDWSCYFRJBA2SF/graph.json","fetch_events":"https://pith.science/api/pith-number/24CFZMU4QQSDJDWSCYFRJBA2SF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF/action/storage_attestation","attest_author":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF/action/author_attestation","sign_citation":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF/action/citation_signature","submit_replication":"https://pith.science/pith/24CFZMU4QQSDJDWSCYFRJBA2SF/action/replication_record"}},"created_at":"2026-05-17T23:39:36.985057+00:00","updated_at":"2026-05-17T23:39:36.985057+00:00"}